Search or ask a question
Pricing
Login
Sign up
Home
Notebook
BETA
Literature Review
Copilot
Citation generator
Paraphraser
AI Detector
Chrome Extension
Talk with us
Use on ChatGPT
All figures (12)
Fig. 1. Achievable dynamic energy improvement assuming ¼ 3 and using 1, 2, 3, and 4 processors given the parallel portion’s ratio of a program.
Fig. 2. Normalized “work” and “time.” “Parallel time” is partitioned into serial and parallel regions.
Fig. 8. Minimum total energy at different values for MB. X axis is log-scale.
Fig. 10. Energy improvement at different speedups over sequential execution.
Fig. 9. Optimal energy at the program speedup of x. The thick dotted line shows the sequential machine’s energy consumption (1þ ).
Fig. 11. Minimum energy consumption at different speedups for MA and MB. Plots for three different values are shown: 0.2, 0.4, and 0.6 from left. The thick dotted line shows the sequential machine’s energy consumption (1þ ).
Fig. 12. Ratio of the total energy of MA to that of MB at the maximum program speedup Amdahl’s law dictates. Plots for three different values are shown: 0.2, 0.4, and 0.6 from left.
Fig. 3. Dynamic energy consumption versus serial time for two cases, s ¼ 0:25 and s ¼ 0:5, when N ¼ 4. The bound of t is marked with “X” (when fs ¼ Fmax ¼ 1) and “O” (when fp ¼ Fmax ¼ 1). The minimum energy point in each curve (at t ¼ t ) is marked with a filled rectangle.
Fig. 13. “Work” is partitioned into speed-scaled work (“n”) and nonspeed-scaled work (“m”). Given N processors, tm, the parallel time for m is m ðsþ p=NÞ regardless of processor speeds.
Fig. 4. changes the speedup of a program when its energy consumption is minimized. We assume that ¼ 3.
Fig. 5. Optimal energy at the program speedup of x when ¼ 3. The thick dotted line shows the sequential machine’s energy consumption (1þ ).
Fig. 6. Energy improvement at different speedups over sequential execution.
Journal Article
•
DOI
•
On the Interplay of Parallelization, Program Performance, and Energy Consumption
[...]
Sangyeun Cho
1
,
Rami Melhem
1
•
Institutions (1)
University of Pittsburgh
1
01 Mar 2010
-
IEEE Transactions on Parallel and Distributed Systems